Search

Research on the Spatiotemporal Evolution Characteristics and Prediction of Long-Term Ground Subsidence along Subway Lines based on SBAS-InSAR and RNN Models

Author(s)

Xin Zhang1, Yitong Wu1, Zhaozhao Lu2,*

Affiliation(s)

1China Jikan Research Institute of Engineering Investigations and Design Co., Ltd., Xi’an, Shaanxi, China 2Shannxi Nongfa Digital Intelligence Group, Xi’an, Shaanxi, China *Corresponding Author

Abstract

Land subsidence has long threaened the safety of construction, operation and maintenance of urban rail transit, and subsidence along subway lines is directly critical to the full life-cycle safety of subway projects. To reveal the spatiotemporal evolution law of land subsidence along subway lines and achieve accurate prediction of subsidence trends, this study takes a subway line in Xi’an as a case. Using 67 Sentinel-1A images (2018.01–2025.03), we extracted long-term subsidence via SBAS-InSAR (validated by second-order leveling), analyzed its spatial distribution along subway line, and built an RNN model to predict subsidence at typical stations. Results show SBAS-InSAR agrees with leveling within ±3 mm (high reliability). Cumulative subsidence (2018–2025) ranges from 60 mm to −252.49 mm, with strong spatial heterogeneity along the Line and the most severe subsidence at Qujiang area. The RNN effectively captures diverse subsidence patterns and accurately predicts severe, stable, and decelerating trends, with predicted and observed evolutions highly consistent. This study provides data and technical support for construction optimization, operational hazard early warning, and subsidence control of Xi’an Subway Line and similar projects in Xi’an.

Keywords

SBAS-InSAR; Land Subsidence; Recurrent Neural Network (RNN); Subsidence Prediction

References

[1]Yin Y, Zhang Z, Zhang K. Land Subsidence and Countermeasures for its Prevention in China. The Chinese Journal of Geological Hazard and Control, 2005, (02):1-8. [2]Wu J. Method and Application of Land Subsidence Disaster Regionalization, SHANGHAI LAND & RESOURCES. 2011, 32(02): 84-7. [3]Ge D. Research on the Key Techniques of SAR Interferometry for Regional Land Subsidence Monitoring. China University of Geosciences (Beijing), 2013. [4]Zhang S, Li M, Liu Z, et al. Temporal and Spatial Distribution Characteristics of Land Subsidence in Xi'an-Xianyang Interpreted by Time-Series InSAR. Journal of Geodesy and Geodynamics. 2024, 44 (04):391-397. [5]Li J, Zhang S, Sheng L, et al. Research on Ground Subsidence Monitoring in Xi'an using Time-series InSAR and Universal GNSS. Bulletin of Surveying and Mapping. 2026, (01):18-24+46. [6]Ferretti A, Prati C, Rocca F. Permanent scatterers in SAR Interferometry. IEEE Transactions on Geoscience & Remote Sensing, 2001, 39(1):8-20. [7]Gabriel A K, Goldstein R M, Zebker H A. Mapping Small Elevation Changes over Large Areas: Differential Radar Interferometry. Journal of Geophysical Research Solid Earth, 1989, 94(B7):9183-9191. [8]Massonnet D, Feigl K L. Radar Interferometry and its Application to Changes in the Earth's Surface. Reviews of Geophysics, 1998. [9]Qu F, Zhang Q, et al. Land Subsidence and Ground Fissures in Xi'an, China 2005–2012 Revealed by Multi-band InSAR Time-series Analysis. Remote Sensing of Environment, 2014, 155:366-376. [10]Chen G, Shan X, Woolk M Moon, et al. A modeling of the magma chamber beneath the Changbai Mountains volcanic area constrained by InSAR and GPS derived deformation. Chinese Journal of Geophysics. 2008, (04): 1085-92. [11]Wan Y, Shen Z, Wang M, et al. Coseismic Slip Distribution of the 2001 Kunlun Mountain Pass West Earthquake Constrained using GPS and InSAR data. Chinese Journal of Geophysics. 2008, (04): 1074-84. [12]Berardino P, Fornaro G, Lanari R, et al. A New Algorithm for Surface Deformation Monitoring Based on Small Baseline Differential SAR Interferograms. IEEE Transactions on Geoscience & Remote Sensing, 2002, 40(11):2375-2383. [13]Deng W, Deng L. Cao S. Application of SBAS-InSAR and ARIMA Models in Monitoring Subway Line Settlement: A Case Study of Urumqi. Urban Rapid Rail Transit, 2025, 38(6): 55-62. [14]Yu S, Chen L. Yang Y, et al Application of InSAR technology in deformation monitoring of Hefei subway. Science of Surveying and Mapping, 2022, 47(3): 96-10, 109. [15]Liu K S, Gong H L, Chen B B. Monitoring and Analysis of Land Subsidence of Beijing Subway Line 6 based on InSAR Data. Journal of Geo-information Science, 2018, 20(1):128-137. [16]Qiao S, Sun C, Bi L et al. Analysis of Settlement Monitoring along the Subway Line in Nanjing based on Time Series InSAR Technology. Bulletin of Surveying and Mapping, 2024, (10):64-70. [17]Han K, Leng L, Zhang J, et al. Spatio-temporal Analysis of Surface Subsidence along the Futian Subway Line based on Time-series InSAR Technology. Bulletin of Surveying and Mapping, 2025, (S2):89-93+179. [18]Chen A, Tan Y, Yang C, et al. Deformation Monitoring along Fuzhou Subway Line based on Radar Technology. Surveying and Mapping Science. 2021(7): 86-91. [19]Hooper A, Zebker H, Segall P et al. A new method for measuring deformation on volcanoes and other natural terrains using InSAR persistent scatterers. Geophysical Research Letters, 2004, 31(23). [20]Shao Y, Ma J, Han L, et al. Time series analysis and prediction of surface subsidence based on SBAS-InSAR technology. Bulletin of Surveying and Mapping, 2025, (04):51-57+62. [21]Zhao C, Zhang Q, Ding X, et al. InSAR Based Evaluation of Land Subsidence and Ground Fissure Evolution at Xi'an. Journal of Engineering Geology. 2009, 17(03): 389-93.